discuss-claims

discuss-claims is a skill for Claude Code, Codex from letitbk/claude-academic-setup. It costs 58 tokens per session (1,440 once invoked), scanned A, original, MIT.

A workflow for creating GitHub issues that let a research team discuss the main findings of a paper. Each issue explains one claim, its evidence, meaning, implications, and limits.

In plain words
What is it for?
Use it to prepare internal GitHub discussions about empirical claims, including links to figures or tables. It is intended for completed analyses in a private or otherwise suitable repository.
Why use it?
It turns completed analysis outputs into focused discussion threads for co-authors instead of leaving findings scattered across files or messages. It also checks that the repository is ready before posting.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

Good fit Use it to prepare internal GitHub discussions about empirical claims, including links to figures or tables. It is intended for completed analyses in a private or otherwise suitable repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/letitbk/claude-academic-setup/discuss-claims
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add letitbk/claude-academic-setup --skill discuss-claims
Clone the repo
git clone --depth 1 https://github.com/letitbk/claude-academic-setup

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for discuss-claims

README.md
[![agentmods](https://agentmods.dev/badge/skills/letitbk/claude-academic-setup/discuss-claims/github.svg)](https://agentmods.dev/skills/letitbk/claude-academic-setup/discuss-claims)
Your own site
<a href="https://agentmods.dev/skills/letitbk/claude-academic-setup/discuss-claims"><img src="https://agentmods.dev/badge/skills/letitbk/claude-academic-setup/discuss-claims/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for discuss-claims

Your own site · 80×15
<a href="https://agentmods.dev/skills/letitbk/claude-academic-setup/discuss-claims"><img src="https://agentmods.dev/badge/skills/letitbk/claude-academic-setup/discuss-claims.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01440
Opus 5 $0.00029 $0.00720
Sonnet 5 $0.00012 $0.00288
Haiku 4.5 $0.00006 $0.00144

Measured 11d ago against content hash b0700ac7f7a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

discuss-claims scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/discuss-claims/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discuss Claims

Post self-contained GitHub issues for internal team discussion of core empirical claims. Each issue covers one claim: motivation, methods, findings (with inline figure/table links), interpretation, implications, and limitations.

When to Use

  • User wants to share analysis findings with co-authors via GitHub Issues
  • User says "post issues", "create claim issues", "discuss on GitHub", "set up review"
  • Analysis pipeline is complete and output files exist

When NOT to Use

  • User wants a formal reviewer template with feedback/decision boxes (this skill creates discussion threads, not review forms)
  • Repo is public and findings are embargoed
  • Output files have not been generated yet

Workflow

Phase 0: Pre-flight

Run these checks before touching GitHub. Fix any failures before proceeding.

# 1. Issues enabled?
gh repo view OWNER/REPO --json hasIssuesEnabled

# 2. Existing [DISCUSS] issues?
gh issue list --state open | grep "\[DISCUSS\]"

# 3. Find untracked output files and auto-commit them
git ls-files --others --exclude-standard output/
# If any exist: git add output/ && git commit -m "Add output files for co-author review" && git push

CRITICAL — broken links are the #1 failure mode: GitHub blob links return 404 if the file is not committed and pushed. Always verify with git ls-files --error-unmatch <file> for at least a sample of referenced figures/tables before creating any issue.

Phase 1: Collect Project Metadata

Infer from git or ask the user:

  • GitHub repo: owner/repo (infer from git remote get-url origin)
  • Branch: master or main (infer from git symbolic-ref refs/remotes/origin/HEAD)
  • Output directories: where figures and tables live (default: output/figures/, output/tables/)

Construct the base blob URL:

https://github.com/OWNER/REPO/blob/BRANCH/PATH/TO/file.png

Phase 2: Discover Output Files

Scan the output directories and build a menu for the user to pick from per claim:

Read the full file on GitHub · 149 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 149 lines · 58 tokens per session scan A b0700ac7f7a0

Subscribe to this mod's changes

discuss-claims is a skill published in the GitHub repository letitbk/claude-academic-setup (45 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,440 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories